Stay updated with the latest research and technology news
arXiv:2504.05695v5 Announce Type: replace Abstract: We prove that overparametrized neural networks are able to generalize with a test error that is independent of the level...
arXiv:2504.08704v2 Announce Type: replace Abstract: Effective leveraging of real-world driving datasets is crucial for enhancing the training of autonomous driving systems. While Offline Reinforcement Learning...
arXiv:2504.12905v3 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) is widely used for novel view synthesis due to its high rendering quality and fast inference...
arXiv:2504.13393v3 Announce Type: replace Abstract: Ground beetles are a highly sensitive and speciose biological indicator, making them vital for monitoring biodiversity. However, they are currently...
arXiv:2504.14129v3 Announce Type: replace Abstract: The challenge of tracing the source attribution of forged faces has gained significant attention due to the rapid advancement of...
arXiv:2504.16946v4 Announce Type: replace Abstract: Generative agents offer promising capabilities for simulating realistic urban behaviors. However, existing methods oversimplify transportation choices, rely heavily on static...
arXiv:2504.19327v3 Announce Type: replace Abstract: Hyperscaling of data and parameter count in LLMs is yielding diminishing improvement when weighed against training costs, underlining a growing...
arXiv:2504.20082v2 Announce Type: replace Abstract: The primary goal of this study is to analyze agentic workflows in education according to the proposed four major technological...
arXiv:2504.20477v3 Announce Type: replace Abstract: Robotic systems increasingly operate in dynamic, unpredictable environments, where tightly coupled sensors and software modules increase the probability of a...
arXiv:2504.21624v3 Announce Type: replace Abstract: Given a graph $G$, a set $T$ of terminal vertices, and a demand graph $H$ on $T$, the \textsc{Multicut} problem...
arXiv:2505.00003v2 Announce Type: replace Abstract: Psychological insights have long shaped pivotal NLP breakthroughs, from attention mechanisms to reinforcement learning and social modeling. As Large Language...
arXiv:2505.02380v4 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose...
arXiv:2505.02831v5 Announce Type: replace Abstract: Recent studies have demonstrated that learning a meaningful internal representation can accelerate generative training. However, existing approaches necessitate to either...
arXiv:2505.03400v2 Announce Type: replace Abstract: As the population continues to age, a shortage of caregivers is expected in the future. Dressing assistance, in particular, is...
arXiv:2505.04076v2 Announce Type: replace Abstract: A dealer aims to share a secret with participants so that only predefined subsets can reconstruct it, while others learn...
arXiv:2505.06835v3 Announce Type: replace Abstract: Sliced optimal transport (SOT), or sliced Wasserstein (SW) distance, is widely recognized for its statistical and computational scalability. In this...
arXiv:2505.07683v4 Announce Type: replace Abstract: The Cancer Genome Atlas (TCGA) has enabled novel discoveries and served as a large-scale reference dataset in cancer through its...
arXiv:2505.08905v3 Announce Type: replace Abstract: Language Models (LMs) continue to advance, improving response quality and coherence. Given Internet-scale training datasets, LMs have likely encountered much...
arXiv:2505.09862v3 Announce Type: replace Abstract: We explore potential benefits of incorporating Rhetorical Design into the design of Explainable Artificial Intelligence (XAI) systems. While XAI is...
arXiv:2505.10571v5 Announce Type: replace Abstract: While Large Language Models (LLMs) excel in reasoning, whether they can sustain persistent latent states remains under-explored. The capacity to...
arXiv:2505.11320v2 Announce Type: replace Abstract: Scam contracts on Ethereum have rapidly evolved alongside the rise of DeFi and NFT ecosystems, utilizing increasingly complex code obfuscation...
arXiv:2505.11708v2 Announce Type: replace Abstract: Reinforcement Learning (RL) agents are increasingly used to simulate sophisticated cyberattacks, but their decision-making processes remain opaque, hindering trust, debugging,...
arXiv:2505.11998v4 Announce Type: replace Abstract: Catastrophic forgetting has remained a critical challenge for deep neural networks in Continual Learning (CL) as it undermines consolidated knowledge...
arXiv:2505.12025v2 Announce Type: replace Abstract: In many real-world applications, users rely on natural language instructions to guide large language models (LLMs) across a wide range...